The research team set out to compare five competing approaches for detecting polygenic adaptation from time-series data on allele frequency changes. Three of these were single methods: the Fisher’s Exact Test, a venerable statistical workhorse that compares allele counts between sampling time points; a Naive Bayesian Classifier, a probabilistic machine learning model that assigns observations to categories based on learned feature distributions; and a One-Class Support Vector Machine, an anomaly-detection algorithm that learns the shape of ‘normal’ neutral evolution and flags deviations from it. The remaining two approaches were hybrids, combining the machine learning models with the classical test to produce OCSVM-FET and NBC-FET. The logic behind the hybrids is intuitive but powerful. The Fisher’s Exact Test is sensitive to statistically significant allele frequency shifts at individual loci, while the machine learning models can integrate patterns across features and recognize the subtle, correlated structure that polygenic selection imposes on many loci at once. By combining the two kinds of evidence, the hybrid methods can filter out noise that would fool either approach alone.

A crucial challenge in this field is that real genomes under known selection pressures are hard to come by. In natural populations, researchers rarely know which loci are actually under selection, how strong the selection is, or when it began, which makes it nearly impossible to judge whether a detection method is working. The authors therefore turned to simulated data generated within an evolve-and-resequence framework, a design in which researchers can specify the exact evolutionary scenario, including the number of loci under selection, the strength of selection, the number of generations, and the timing of genomic sampling, and then evaluate how well each method recovers the truth. The simulations were parameterized using empirical Pool-Seq data from the non-biting midge Chironomus riparius, an organism well suited to experimental evolution studies, which grounds the synthetic scenarios in biologically realistic levels of genetic variation and demographic noise.

Pool-Seq itself deserves a brief technical explanation, because it shapes both the strengths and the limitations of the data. Rather than sequencing individual organisms separately, Pool-Seq sequences an entire population sample together, estimating allele frequencies from the pooled reads. This makes time-series sampling affordable: researchers can sequence a population at generation zero, generation ten, generation twenty, and so on, tracking how allele frequencies shift over time. For detecting selection, these temporal trajectories are gold, because neutral drift produces random walk-like fluctuations while selection produces directional, consistent shifts. However, Pool-Seq introduces its own measurement uncertainty, since read depth and pooling noise mean that estimated frequencies are never exact. Any detection method must therefore distinguish genuine selective signals from both stochastic drift and sampling error, a task that becomes exponentially harder when the per-locus effects of selection are as small as those expected under polygenic adaptation.

The evaluation across scenarios varying in generation number, selection strength, and the number of selected loci produced a clear ranking. The combined OCSVM-FET approach achieved the lowest false positive rate, the highest area under the receiver operating characteristic curve, and high overall accuracy, consistently outperforming the standalone machine learning models, the standalone Fisher’s Exact Test, and the alternative NBC-FET hybrid. In practical terms, this means that when the OCSVM-FET method flags a locus or a pattern as being under selection, that flag is more likely to be real, and the method captures a larger fraction of the true targets, than any of the competing approaches tested. For experimental evolutionists planning expensive sequencing campaigns, this reduction in false positives is not a statistical nicety; it directly determines which candidate loci get followed up and how much laboratory validation is required.

Perhaps the most biologically interesting result concerns timing. The performance of the winning method peaked during what the authors call the ‘late dynamic phase’ of adaptation, the window after selection has begun to shift allele frequencies but before the favored variants have reached fixation. This makes deep evolutionary sense. Early in adaptation, allele frequency changes are so small that they drown in drift and sampling noise, and even the best methods have little to work with. Late in adaptation, once beneficial alleles have fixed, the variation that methods rely on has been erased, and the signal vanishes again. The late dynamic phase is the sweet spot in between, where selection has produced measurable, directional movement at many loci while sufficient polymorphism remains for statistical tests and machine learning models to detect structure. The finding carries an immediate practical message for experimental design: temporal sampling schemes should be tuned to capture this phase, because sequencing too early or too late can render even a superior method blind.

The study also delivers a sobering lesson about parameter tuning, which the authors describe as critical and as a matter of balancing biological assumptions against methodological rigor. Machine learning models are not plug-and-play devices; the One-Class Support Vector Machine, for instance, requires choices about kernel functions, nu parameters, and the feature representation of the data, and each of these choices encodes implicit assumptions about what neutral evolution looks like and how selection deviates from it. Set the parameters too loosely and the model flags noise as signal; set them too tightly and genuine adaptation slips through. The authors emphasize that these choices must be informed by the biology of the system, including realistic effective population sizes, mutation rates, and the expected architecture of the trait under selection, rather than by generic defaults. This is a point that resonates well beyond this particular study, as machine learning methods proliferate across genomics faster than the standards for validating and tuning them.

The authors are careful about scope, and that caution matters for how the results should be used. The benchmarking was intentionally designed and validated for evolve-and-resequence experimental contexts, where defined selection pressures and temporal sampling are feasible, and the authors note that applicability to certain natural experiments might be possible but remains to be demonstrated. Natural populations present complications that the controlled simulations do not fully capture: population structure, admixture, changing demography, and unknown and heterogeneous selection regimes can all mimic or mask polygenic signals. Extending the framework to those settings is explicitly flagged as an important direction for future work. Until then, the strongest claims apply to laboratory and semi-natural experimental evolution studies, which are, fortunately, a growing and increasingly important part of evolutionary genomics, particularly for questions about rapid adaptation to environmental change.

The broader significance of this work lies in what it suggests about the future of method development in evolutionary biology. For decades, the field has relied on a relatively small toolkit of statistical tests, each with well-understood assumptions and limitations. Machine learning offers a way to move beyond single-locus tests toward classifiers that integrate many weak signals into a coherent decision, but the study shows that the most effective strategy is not replacement but combination. The classical test contributes a well-calibrated measure of per-locus evidence; the machine learning model contributes pattern recognition across loci and features; and the fusion of the two achieves better discrimination than either alone. This hybrid philosophy, in which old and new methods are treated as complementary sources of evidence rather than rivals, may prove to be a template for tackling other detection problems in genomics where signals are subtle, distributed, and easily drowned by noise.

For researchers working on experimental evolution, the study provides an actionable benchmark: when designing evolve-and-resequence experiments aimed at dissecting the genomic basis of quantitative traits, the OCSVM-FET approach currently offers the best validated performance for detecting polygenic adaptation from Pool-Seq time series, provided that sampling captures the late dynamic phase and that parameters are tuned to the biology of the study organism. For the wider community, the message is that the era of polygenic adaptation detection, long hampered by the sheer subtlety of the signal, may be entering a more productive phase, one in which carefully benchmarked hybrid methods, grounded in realistic simulations and honest about their limits, replace the optimistic one-size-fits-all tests of the past. As climate change accelerates the pace of adaptation in natural and experimental populations alike, the ability to see those small, distributed shifts in the genome will only grow in importance, and this study marks a meaningful step toward that goal.

Subject of Research: Detection of polygenic adaptation using machine learning and statistical methods on simulated evolve-and-resequence genomic data

Article Title: Enhancing detection of polygenic adaptation: a comparative study of machine learning and statistical approaches using simulated evolve-and-resequence data

Article References: Caliendo, C., Gerber, S., & Pfenninger, M. (2026). Enhancing detection of polygenic adaptation: a comparative study of machine learning and statistical approaches using simulated evolve-and-resequence data. BMC Genomics, 27(1), Article 740. https://doi.org/10.1186/s12864-026-13163-2

Image Credits: AI Generated

DOI: 10.1186/s12864-026-13163-2

Keywords: polygenic adaptation, machine learning, population genomics, evolve-and-resequence, Pool-Seq, One-Class Support Vector Machine, Fisher's Exact Test, allele frequency, experimental evolution, BMC Genomics, false positive rate, time-series genomics

Autism spectrum disorder is a neurodevelopmental condition characterized by differences in social communication, restricted interests, and repetitive behaviors, and its reported prevalence has been climbing steadily worldwide. That rise has intensified the search for modifiable risk factors, yet large gaps remain in the epidemiological record for the Middle East, where region-specific data on both autism risk factors and the oral health of autistic children have been scarce. The new study was designed to fill that gap in one Saudi city, combining a detailed pregnancy and birth history with a careful accounting of each family’s dental care behaviors, from brushing habits to whether the child had ever sat in a dentist’s chair for preventive treatment.

The methodology was deliberately straightforward but statistically disciplined. Mothers completed a structured questionnaire covering demographic details, pregnancy complications, medication use, mode of delivery, and their children’s oral health practices, with each respondent giving informed consent under ethical approval from the College of Dentistry Research Ethics Committee at Taibah University and in accordance with the Declaration of Helsinki. Because the data were largely categorical, the analysis relied on Fisher’s Exact Test to determine whether associations were statistically significant, and on Cramér’s V, a measure that quantifies the strength of an association between two categorical variables, to rank which relationships were most powerful. This two-pronged approach matters, because a finding can be statistically significant yet clinically weak, and the combination of P values and effect sizes gives a far more honest picture of what is actually driving risk.

The first headline finding concerns gestational age, which showed significant associations with several prenatal factors. Maternal medication use during pregnancy emerged as the strongest of these, with a highly significant P value below 0.001 and a Cramér’s V of 0.340, indicating a moderate association with gestational age in this cohort. First-trimester hospitalization was also significantly associated, at P equal to 0.004. These figures do not prove that medication use or early-pregnancy complications cause autism, and the authors are careful to frame them as associations within a single-region cross-sectional sample. But they do flag the first trimester, a period of critical neural tube formation and early brain development, as a window where clinical events cluster among mothers of children with autism in this population, strengthening the case for enhanced perinatal monitoring.

The most eye-catching result in the entire dataset, however, is what statisticians would call a perfect association. The study found a Cramér’s V of 1.000 with a P value below 0.001 between familial recurrence of autism spectrum disorder and perinatal trauma, specifically the combination of assisted vaginal delivery and cerebellar injury. A perfect association means that in this sample, the two variables track each other completely: where one was present, so was the other. The cerebellum, long associated with motor coordination, is now recognized as playing a substantial role in cognition, emotion, and social processing, and cerebellar injury at birth has been repeatedly implicated in neurodevelopmental outcomes. That a complete overlap emerged between family history of autism and traumatic delivery events in 114 participants is remarkable, and while perfect associations in observational data often reflect small-cell patterns rather than universal laws, the finding demands replication and careful clinical attention.

Interpreting this result requires nuance. Familial recurrence could indicate shared genetic vulnerability that also predisposes to difficult labors, or families with a prior autistic child may be systematically monitored and diagnosed differently in subsequent births. Assisted vaginal delivery, involving instruments such as forceps or vacuum extraction, is itself more likely when labor becomes complicated, so the direction of causality is genuinely ambiguous. What the study establishes is a correlation precise enough to warrant follow-up: obstetric teams managing deliveries in families with an existing autism diagnosis may represent a high-priority group for intra-partum vigilance aimed at avoiding birth trauma, particularly to the cerebellum. The authors explicitly frame the finding as grounds for enhanced perinatal monitoring and for managing recurrence risks in the region.

On the dental side of the study, the socioeconomic analysis produced results that challenge common assumptions about access to care. Maternal education was significantly associated with regular dental attendance, at P equal to 0.032, and maternal employment was significant at P equal to 0.013. Family income, by contrast, showed no significant effect whatsoever, with a P value of 0.581. In other words, in this Saudi cohort, whether an autistic child sees a dentist regularly depended not on how much money the family had, but on the mother’s schooling and her participation in the workforce. This is a consequential distinction for health policy, because income-targeted subsidies alone would miss the lever that actually predicts behavior here. The likely mechanism is health literacy: educated mothers are more attuned to preventive care recommendations, better equipped to navigate appointment systems, and more persistent in finding practitioners willing and able to treat autistic children.

One further finding hints at a system-level problem. Dental cooperation, meaning the child’s ability to tolerate examination and treatment, showed a marginal but suggestive trend associated with provider accessibility, at P equal to 0.067. While this falls short of conventional statistical significance, it points toward a familiar clinical reality: autistic children often struggle with the sensory demands of a dental visit, bright lights, unfamiliar instruments, and physical proximity, and practices that are accessible, patient, and trained in behavioral strategies can dramatically change whether treatment is possible. A trend at this level in a sample of 114 should be treated as a signal worth pursuing, not a conclusion, but it aligns with a broader international literature on the oral health disparities faced by children with developmental disabilities, who experience higher rates of caries and gingival disease yet lower rates of preventive care.

Taken together, the study’s conclusions are pointed. Perinatal clinical markers and maternal health literacy outperformed traditional socioeconomic metrics such as family income as predictors of autism-related outcomes in this cohort. The authors advocate for two concrete responses: enhanced perinatal monitoring to identify and mitigate birth-related risks, particularly in families with a history of autism, and targeted maternal education programs designed to improve preventive dental care for autistic children. The work was funded by Taibah University in Madinah under grant number 448-16-1214, with the author also acknowledging contributions from Dr. Nohad El Zein, a maternal fetal medicine specialist, and Dr. Reham Alyami, who supported data collection. Published open access on 22 September 2026, the paper received ethical approval under reference TUCDREC/050124/AAl-Namankany and involved no competing interests.

The broader significance of the study lies in its regional grounding. Most of what the world knows about autism risk factors and the dental care of autistic children comes from North America, Europe, and East Asia, and findings do not always transfer cleanly across health systems and cultures. By supplying statistically characterized evidence from Al Madinah, the research gives Saudi health authorities a local evidence base for intervention, and it gives the international research community a dataset whose striking perinatal findings, especially the perfect association between familial autism recurrence and traumatic delivery, cry out for replication in larger, multi-center cohorts. If subsequent studies confirm these patterns, the implications could reach obstetric wards and dental clinics alike, reshaping how clinicians counsel families and schedule care long before a child’s first dental appointment. For now, the message from Madinah is clear: what happens in the womb and the delivery room, and what a mother knows, may matter more than what a family earns.

Subject of Research: Prenatal and perinatal risk factors for autism spectrum disorder and dental care barriers among autistic children in Al Madinah, Saudi Arabia

Article Title: From womb to wellness: assessment of maternal birth-related risks and dental care among autistic children in Al Madinah, Saudi Arabia

Article References: From womb to wellness: assessment of maternal birth-related risks and dental care among autistic children in Al Madinah, Saudi Arabia. (n.d.). https://doi.org/10.1186/s12887-026-07524-9

Image Credits: AI Generated

DOI: 10.1186/s12887-026-07524-9

Keywords: autism spectrum disorder, perinatal trauma, gestational age, maternal education, dental cooperation, Cramér's V, Fisher's Exact Test, cerebellar injury, oral health, Saudi Arabia, Taibah University, maternal health literacy

The method, described in the journal BMC Bioinformatics by Jack Kamm, Jake Yeung, and William F. Forrest of Genentech, reframes guide assignment as a problem in classical statistics. Rather than fitting an elaborate probabilistic model to the guide count matrix, the authors propose treating the matrix of guide RNA counts across cells as a contingency table. For every cell-guide pair, they construct a two-by-two table that contrasts the counts involving that cell and that guide with all other counts, and then apply Fisher’s Exact Test, a workhorse of categorical data analysis, to ask whether the cell and guide barcodes are statistically associated. A significant association signals that the guide is genuinely present in the cell rather than appearing by chance through sequencing noise.

The elegance of this formulation lies in what it provides automatically. Because Fisher’s Exact Test conditions on the margins of the contingency table, the resulting p-values implicitly normalize for both cell-specific and guide-specific size factors, the uneven sequencing depth that plagues single-cell data. Cells that received more total reads and guides that were more abundant in the library are handled without any explicit normalization step. The method also produces a p-value for every cell-guide pair, giving users a graded measure of confidence rather than a hard binary call, and enabling downstream analyses such as full precision-recall curves when benchmarking alternative cutoffs.

Two statistical subtleties demanded additional innovation. First, because the method performs one test for every cell-guide combination, large screens can involve tens of millions of hypothesis tests. Naive application of standard multiple testing corrections such as the Benjamini-Hochberg procedure would be inappropriate, because the tests are strongly correlated: a cell that tests positive for one guide is less likely to test positive for others, and counts involving the same guide or the same cell share information. The authors developed a multiple testing correction strategy that accounts for this correlation structure, preserving control of the false discovery rate while avoiding the excessive conservatism that would come from ignoring the dependencies.

The second subtlety is a form of confounding that can flip conclusions in exactly the wrong way. Ambient RNA contamination, sometimes called soup or background noise, introduces guide molecules into cells that never received them. If the contamination is not independent across cells and guides, a phenomenon analogous to Simpson’s paradox can arise: an association that appears significant in the aggregate data disappears, or even reverses, once the noise component is considered separately. Fishash addresses this by testing an adjusted odds ratio that replaces the margins involving the focal cell and guide with their noise-based counterparts. To estimate the unobserved noise counts, the method performs an iterative rank-1 Poisson matrix completion: entries that have already been confidently assigned are masked out, the remaining background structure is fit under a Poisson likelihood by alternating updates of guide and cell abundance parameters, and the imputed noise counts feed back into refined p-values. The procedure repeats until the assignments stabilize.

Recognizing that fair comparison of guide assignment methods has been hampered by a lack of realistic test data, the authors also introduced a simulation framework that generates synthetic guide counts under a detailed model of sequencing noise. The simulator draws on the contamination model popularized by the Cellbender software, incorporating latent cell-level factors such as ambient RNA fractions, capture efficiencies, and dropout rates, along with guide-level expression variation. Crucially, the simulations can vary the number of guides in the library and the multiplicity of infection, the average number of guides delivered per cell, allowing benchmarking across the parameter regimes that matter in practice. The code to reproduce all results is publicly available alongside the method itself.

In benchmarks on both simulated and real datasets, Fishash compared favorably with existing approaches in both accuracy and runtime. On simulations varying the number of guides, the method achieved the top median F1 score in the majority of settings, performing particularly well when the guide library was large or guide RNA expression was low. In simulations varying the multiplicity of infection, Fishash remained competitive at low multiplicity, where most cells carry at most one guide, though other methods such as crispat-NB and dcCLEANSER edged ahead at high multiplicity. The authors emphasize that Fishash was conservative in its error control: its observed precision stayed above its nominal lower bound across the sweep, whereas several competing Bayesian and frequentist methods failed to control the false discovery rate at least once across the scenarios tested.

The stress tests also revealed the method’s limits, which the authors report transparently. When extra overdispersion was injected into the noise counts by replacing the Poisson distribution with a Geometric distribution, one of the most extreme overdispersion regimes available, precision dropped for many methods and Fishash no longer controlled the false discovery rate at its nominal five percent level in every scenario. Even so, its F1 scores remained qualitatively similar to the original benchmarks, indicating a competitive balance between precision and recall even under unusually harsh noise. The authors note that the conditional low-rank Poisson structure assumed for background counts is common to many single-cell contamination models, including Cellbender, SoupX, DecontX, and scAR, so the simulation represents a deliberately challenging departure from the assumptions shared across the field.

Practical accessibility was a design priority. Fishash is distributed as an easy-to-use R package on GitHub, and because it relies on exact tests over contingency tables rather than iterative model fitting, it scales comfortably to screens with tens of thousands of cells and guides, where computationally expensive probabilistic approaches can become prohibitive. The software also outputs its test statistic for every entry of the cell-guide matrix, which allows users to visualize the distribution of scores, select alternative significance cutoffs informed by the data, and compute full precision-recall curves during method benchmarking. The work was carried out entirely within Genentech, with the authors crediting colleagues in the company’s AI Biology and Translation department for discussions that shaped the manuscript.

For the growing community running Perturb-seq experiments, the significance of the method is straightforward: guide assignment is the gatekeeper step that determines whether downstream perturbation effects are real or artifacts of misassignment, and errors made here propagate through every subsequent analysis. By combining a classical, well-understood statistical test with modern corrections for multiplicity, confounding, and background contamination, and by packaging the result in fast, open software, Fishash lowers both the computational and conceptual barriers to reliable pooled single-cell screening. As CRISPR screens continue to expand in scale and ambition, tools that trade heavy model fitting for careful, assumption-aware statistics are likely to play an increasingly central role in turning raw sequencing counts into trustworthy biological conclusions.

Subject of Research: A contingency table and Fisher's Exact Test based method for assigning guide RNAs to cells in single-cell pooled CRISPR screens (Perturb-seq)

Article Title: Fishash: a contingency table approach to Perturb-seq guide assignment

Article References: Kamm, J., Yeung, J., & Forrest, W. F. (2026). Fishash: a contingency table approach to Perturb-seq guide assignment. BMC Bioinformatics. https://doi.org/10.1186/s12859-026-06631-9

Image Credits: AI Generated

DOI: 10.1186/s12859-026-06631-9

Keywords: Perturb-seq, CRISPR screen, single-cell RNA-seq, guide assignment, Fisher's exact test, Simpson's paradox, multiple testing correction, contingency table, false discovery rate, ambient RNA contamination, functional genomics, BMC Bioinformatics